oah helps you build an AI development workflow that fits you and keeps changing as AI improves. It is a working reference and a guide you can adapt.
A useful result needs more than generated code: the scope must be clear, the changes checked, and decisions kept for the next session. oah connects those steps so one request can carry through the work with a record of what happened.
002 / Why it keeps changing
Older rules and skills can hold a newer model back or make its results worse. Defaults should be easy to understand and change; a rule that gets in your way is a design problem to fix.
Keep the parts that help, remove what no longer helps, and revise the workflow as your tools improve. You can start with the full setup or take only the impact map, wiki, leases, evidence gates or review loop that your project needs.
003 / Why Claude builds and Codex reviews
This split comes from the author's own experience, not a measured comparison: Claude fills in details a beginner might miss in a first version; Codex checks and corrects within a fixed scope.
The current commands run Claude Code and Codex CLI. The ideas can also be adapted to another tool or harness, with one AI or several. Give each stage to the AI that suits your work.
004 / From one request to a checked change
Describe the result you want in plain language. The AI records the goal and scope, checks what the change touches, reserves its paths and chooses the tools for the task. Claude builds; Codex reviews, corrects and reviews again.
Gates record the checks and their results. The project wiki keeps the decisions and reasons beside the code. In v0.3.0, optional TypeSafe Jev can judge difficulty for model selection; rules remain the fallback when it is unavailable or uncertain.
005 / The decisions stay with you
You ask, answer when the AI needs a decision, and confirm before the change lands. If the same problem repeats or the work reaches a design choice, the loop stops to ask you.
Ask “Is the review done?” or “Did all the gates pass?” and inspect the evidence. The final confirmation belongs to you; writing code, checking it and approving its landing are separate steps.
006 / Free, open source, yours to adapt
oah is free, open-source software under the MIT license. Read the source, change it and bring the useful pieces into your own workflow. Your AI services and any optional services use their own accounts and billing.
The current v0.3.0 release supports macOS and native Windows, and expects familiarity with git and pull requests. Install it, run oah init in your project, then try the small hello-oah example. The installation and documentation sections explain each step.
TypeSafe Jev is the recommended, optional judge. It re-orders chosen skills and, in v0.3.0, judges difficulty from the Intent and Scope paths. Its tier guides model choice, subject to confidence thresholds and minimum tiers. Without a key, with Jev off or with an uncertain answer, the rules decide.
When you need it
Fixed rules score a task from its Scope alone, so their skill order and model choice can miss what a task really needs. A judge can help, but it must never become a hidden requirement or bypass the rules.
How it works
oah init asks once whether to enable it, and you can enable it later in .oah/config.toml. It runs only when you enabled it and the key is present; a key alone never turns it on.
Ranking: Jev re-orders the closed skill list produced by the rules. It never adds or drops a candidate.
Model choice: Jev can pick a model and effort only from candidates the rules allow, subject to model pins, qualified pools, supported effort and the task's minimum requirements.
Every packet plan, brief, run record and impact result says rerank=used or rerank=unused(<reason>), such as not-enabled, no key or disabled-by-brief.
In v0.3.0, Jev also judges difficulty from the accepted Intent and Scope paths; its tier must meet the confidence threshold and never go below the floor.
Example
What `oah init` records when you enable the re-ranker (from Keys).
[rerank]
enabled = true
provider = "typesafe"
Requirements
Your own TypeSafe account and TYPESAFE_API_KEY, stored in an environment variable or the OS keychain.
oah doctor does not check Jev's state; the rerank= results show it.
Limits and recovery
TypeSafe may charge for each request.
Jev cannot invent a candidate or bypass a floor.
Impact-result re-ranking remains planned, not a shipped feature.
Difficulty judgement is subject to confidence thresholds and the task's minimum tier.
--no-rerank, or a packet that turns it off, gives rerank=unused(disabled-by-brief).